fix: video upload flow for Qwen3.5 vLLM chat

[shihanqu]

Pull Request Checklist

• Target branch: Verify that the pull request targets the dev branch. PRs targeting main will be immediately closed.
• Description: Provide a concise description of the changes made in this pull request down below.
• Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
• Documentation: Add docs in Open WebUI Docs Repository. Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps.
• Dependencies: Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash.
• Testing: Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to make screenshots of the feature/fix and include them in the PR description.
• Agentic AI Code: Confirm this Pull Request has gone through additional manual review AND manual testing.
• Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
• Design & Architecture: Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes.
• Git Hygiene: Keep PRs atomic (one logical change). Clean up commits and rebase on dev to ensure no unrelated commits (e.g. from main) are included. Push updates to the existing PR branch instead of closing and reopening.
• Title Prefix: PR title uses the fix: prefix.

Changelog Entry

Description

• Fixes OpenAI-compatible multimodal video upload flow in chat by ensuring uploaded video/* files are injected into the outgoing message payload as video_url parts and media URLs are converted to base64 for both images and videos when needed.
• Removes misleading upload-processing failure for video/mp4 by treating video uploads as completed for multimodal chat usage rather than forcing retrieval/text extraction processing.
• Specifically allows compatibility with Qwen3.5 video input when Open WebUI is connected to vLLM. Have not tested other multimodal LLMs.
• I have personally tested this change by uploading a few videos with Qwen3.5 397B loaded in a local instance of vLLM.

Added

• Support in process_chat_payload for injecting uploaded video files as {"type":"video_url", "video_url":{"url":...}} content parts.
• Support in media URL conversion for both image_url and video_url items.

Changed

• Renamed convert_url_images_to_base64 to convert_url_media_to_base64 and generalized handling from image-only to image+video.

Deprecated

• None.

Removed

• None.

Fixed

• Fixed upload-time warning/error path where valid video/mp4 chat uploads were marked as unsupported for processing.
• Fixed missing propagation of uploaded videos into OpenAI-compatible multimodal request content.

Security

• No security behavior changes.

Breaking Changes

• BREAKING CHANGE: None.

---

Additional Information

• No new dependencies introduced.
• Manual validation performed in a real Docker deployment with vLLM backend.
• Linked documentation PR: docs: clarify vLLM video upload and source indicator behavior docs#1130
• Validation used the official Qwen3.5 demo video from the model documentation:
  • Video: https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/video/N1cdUjctpG8.mp4
  • Qwen model docs: https://huggingface.co/Qwen/Qwen3.5-397B-A17B
• Repro steps used during validation:
  1. Upload the video in Open WebUI chat.
  2. Verify no upload failure toast for video/mp4 processing.
  3. Send prompt to vLLM-backed Qwen3.5 model.
  4. Confirm model returns accurate video interpretation.
• "No sources found" may still appear for video-only turns because no RAG citations are attached; this is expected and unchanged by this PR.

Screenshots or Videos

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.

[pr-validator-bot]

👋 Welcome and Thank You for Contributing!

We appreciate you taking the time to submit a pull request to Open WebUI!

⚠️ Important: Testing Requirements

We've recently seen an increase in PRs that have significant issues:

• PRs that don't actually fix the bug they claim to fix
• PRs that don't implement the feature they describe
• PRs that break existing functionality
• PRs that are clearly AI-generated without proper testing being done by the author
• PRs that simply don't work as intended

These untested PRs consume significant time from maintainers and volunteer contributors who review and test PRs in their free time.
Time that could be spent testing other PRs or improving Open WebUI in other ways.

Before marking your PR as "Ready for Review":

Please explicitly confirm:

1. ✅ You have personally tested ALL changes in this PR
2. ✅ How you tested it (specific steps you took to verify it works)
3. ✅ Visual evidence where applicable (screenshots or videos showing the feature/fix working) - if applicable to your specific PR

If you're not certain your PR works exactly as intended, please leave it in DRAFT mode until you've thoroughly tested it.

Thank you for helping us maintain quality and respecting the time of our community! 🙏